中文
相关论文

相关论文: ReasoningGuard: Safeguarding Large Reasoning Model…

200 篇论文

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

人工智能 · 计算机科学 2026-02-03 Jingnan Zheng , Jingjun Xu , Yanzhen Luo , Chenhang Cui , Gelei Deng , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms…

人工智能 · 计算机科学 2026-01-08 Su-Hyeon Kim , Hyundong Jin , Yejin Lee , Yo-Sub Han

Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose great safety risks against harmful queries and adversarial…

人工智能 · 计算机科学 2025-11-18 Kaiwen Zhou , Xuandong Zhao , Gaowen Liu , Jayanth Srinivasa , Aosong Feng , Dawn Song , Xin Eric Wang

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

人工智能 · 计算机科学 2025-10-27 Jingnan Zheng , Xiangtian Ji , Yijun Lu , Chenhang Cui , Weixiang Zhao , Gelei Deng , Zhenkai Liang , An Zhang , Tat-Seng Chua

While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text. Existing defensive…

计算与语言 · 计算机科学 2024-12-30 Yilei Jiang , Yingshui Tan , Xiangyu Yue

Large Reasoning Models (LRMs) have recently demonstrated impressive performances across diverse domains. However, how the safety of Large Language Models (LLMs) benefits from enhanced reasoning capabilities against jailbreak queries remains…

计算与语言 · 计算机科学 2025-09-23 Junda Zhu , Lingyong Yan , Shuaiqiang Wang , Dawei Yin , Lei Sha

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

人工智能 · 计算机科学 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating…

人工智能 · 计算机科学 2025-08-29 Yuanzhe Shen , Zisu Huang , Zhengkang Guo , Yide Liu , Guanxu Chen , Ruicheng Yin , Xiaoqing Zheng , Xuanjing Huang

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

人工智能 · 计算机科学 2026-01-27 Xin Gao , Shaohan Yu , Zerui Chen , Yueming Lyu , Weichen Yu , Guanghao Li , Jiyao Liu , Jianxiong Gao , Jian Liang , Ziwei Liu , Chenyang Si

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

计算与语言 · 计算机科学 2025-10-16 Changyi Li , Jiayi Wang , Xudong Pan , Geng Hong , Min Yang

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

人工智能 · 计算机科学 2025-10-21 Zhehao Zhang , Weijie Xu , Shixian Cui , Chandan K. Reddy

Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. In particular, while algorithms are designed to guide them to…

机器学习 · 计算机科学 2026-02-05 Zeming Wei , Qiaosheng Zhang , Xia Hu , Xingcheng Xu

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

机器学习 · 计算机科学 2025-04-15 Junfeng Fang , Yukai Wang , Ruipeng Wang , Zijun Yao , Kun Wang , An Zhang , Xiang Wang , Tat-Seng Chua

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

密码学与安全 · 计算机科学 2026-03-04 Zhen Guo , Shanghao Shi , Hao Li , Shamim Yazdani , Ning Zhang , Reza Tourani

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

计算与语言 · 计算机科学 2025-10-14 Xinyue Lou , You Li , Jinan Xu , Xiangyu Shi , Chi Chen , Kaiyu Huang

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional…

人工智能 · 计算机科学 2026-05-20 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Yuzhe Huang , Haichang Gao

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

人工智能 · 计算机科学 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes domains such as healthcare and education. While prior…

机器学习 · 计算机科学 2026-04-20 Zehao Wang , Lanjun Wang
‹ 上一页 1 2 3 10 下一页 ›